Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical spaces and their layout

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.91
    AndEndTag
    -0.88
    UserScript
    -0.83
     utafitiHapana
    -0.83
     فريبيس
    -0.82
     cherchés
    -0.81
     صوتيه
    -0.78
     للمعارف
    -0.76
     okuyayım
    -0.76
    protoimpl
    -0.75
    POSITIVE LOGITS
     room
    0.82
     rooms
    0.81
     spacious
    0.75
     interior
    0.68
     loft
    0.65
     interiors
    0.63
     floor
    0.63
     Room
    0.63
    Попис
    0.61
    room
    0.60
    Act Density 0.040%

    No Known Activations